publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- Worldrft: Latent world model planning with reinforcement fine-tuning for autonomous driving2026Proceedings of the AAAI Conference on Artificial Intelligence 40 (14), 11649 …
- Unifying language-action understanding and generation for autonomous driving2026Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
- StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention2026arXiv preprint arXiv:2603.19552
-
- SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model2026Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
- ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving2026arXiv preprint arXiv:2605.04647
- Planagent: A multi-modal large language agent for closed-loop vehicle motion planning2026IEEE Transactions on Cognitive and Developmental Systems
- Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation2026arXiv preprint arXiv:2606.15869
- Method and apparatus for generating trajectory, electronic device, storage medium2026US Patent App. 19/037,583
- M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models2026arXiv preprint arXiv:2605.09879
-
- Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs2026arXiv preprint arXiv:2602.10377
-
- Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning2026arXiv preprint arXiv:2602.01983
-
- DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving2026Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
- Correctad: A self-correcting agentic system to improve end-to-end planning in autonomous driving2026Proceedings of the AAAI Conference on Artificial Intelligence 40 (10), 7755-7763
- Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training2026arXiv preprint arXiv:2605.21372
- Ad-r1: Closed-loop reinforcement learning for end-to-end autonomous driving with impartial world models2026Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
2025
- Transdiffuser: End-to-end trajectory generation with decorrelated multi-modal representation for autonomous driving2025arXiv e-prints, arXiv: 2505.09315
- Transdiffuser: Diverse trajectory generation with decorrelated multi-modal representation for end-to-end autonomous driving2025arXiv preprint arXiv:2505.09315
- The better you learn, the smarter you prune: Towards efficient vision-language-action models via differentiable token pruning2025arXiv preprint arXiv:2509.12594
- StyledStreets: Multi-style Street Simulator with Spatial and Temporal Consistency2025arXiv preprint arXiv:2503.21104
- Streetcrafter: Street view synthesis with controllable video diffusion models2025Proceedings of the Computer Vision and Pattern Recognition Conference, 822-832
- Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives2025IEEE transactions on pattern analysis and machine intelligence
- Recondreamer: Crafting world models for driving scene reconstruction via online restoration2025Proceedings of the Computer Vision and Pattern Recognition Conference, 1559-1569
- PosePilot: Steering camera pose for generative world models with self-supervised depth2025IEEE/RSJ International Conference on Intelligent Robots and Systems …
- Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback2025arXiv preprint arXiv:2503.10434
- HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity2025Proceedings of the IEEE/CVF International Conference on Computer Vision …
- Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction2025Proceedings of the IEEE/CVF International Conference on Computer Vision …
- Geodrive: 3d geometry-informed driving world model with precise action control2025arXiv preprint arXiv:2505.22421
- Generalizing motion planners with mixture of experts for autonomous driving2025IEEE International Conference on Robotics and Automation (ICRA), 6033-6039
-
Finetuning generative trajectory model with reinforcement learning from human feedback2025arXiv e-prints, arXiv: 2503.10434 - Drivingsphere: Building a high-fidelity 4d world for closed-loop simulation2025Proceedings of the Computer Vision and Pattern Recognition Conference, 27531 …
- DriveAgent-R1: Advancing VLM-based autonomous driving with hybrid thinking and active perception2025arXiv e-prints, arXiv: 2507.20879
- DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking2025arXiv preprint arXiv:2507.20879
- Dive: Efficient multi-view driving scenes generation based on video diffusion transformer2025arXiv preprint arXiv:2504.19614
- Discrete diffusion for reflective vision-language-action models in autonomous driving2025arXiv preprint arXiv:2509.20109
- Bev-tsr: Text-scene retrieval in bev space for autonomous driving2025Proceedings of the AAAI Conference on Artificial Intelligence 39 (7), 7275-7283
- 3drealcar: An in-the-wild rgb-d car dataset with 360-degree views2025Proceedings of the IEEE/CVF International Conference on Computer Vision …
2024
- Xiaoxiao Long, Yilun Chen, and Hao Zhao. Tod3cap: Towards 3d dense captioning in outdoor scenes2024Computer Vision–ECCV, 367-384
- Unleashing generalization of end-to-end autonomous driving with controllable long video generation2024arXiv preprint arXiv:2406.01349
- Ua-track: Uncertainty-aware end-to-end 3d multi-object tracking2024arXiv e-prints, arXiv: 2406.02147
- Tod3cap: Towards 3d dense captioning in outdoor scenes2024European Conference on Computer Vision, 367-384
-
Street gaussians: Modeling dynamic urban scenes with gaussian splatting2024European Conference on Computer Vision, 156-173 - S2-track: A simple yet strong approach for end-to-end 3d multi-object tracking2024arXiv preprint arXiv:2406.02147
-
Drivevlm: The convergence of autonomous driving and large vision-language models2024arXiv preprint arXiv:2402.12289 -
-
- Balanced 3DGS: Gaussian-wise parallelism rendering with fine-grained tiling2024arXiv preprint arXiv:2412.17378
2023
2015
- Joint tracking and classification with constraints and reassignment by radar and ESM2015Digital Signal Processing 40, 213-223
2014
- Particle filter based joint tracking and classification2014Proceedings of IEEE Chinese Guidance, Navigation and Control Conference …
- Joint tracking and classification on aerodynamic model and RCS by ground-based passive radar2014Proceedings of IEEE Chinese Guidance, Navigation and Control Conference …
- Joint tracking and classification based on aerodynamic model and radar cross section2014Pattern recognition 47 (9), 3096-3105